Neural Network on Emerging Memory: From Applications to Circuits on ReRAM

Speaker:  Yu Wang – Beijing, China
Topic(s):  Architecture, Embedded Systems and Electronics, Robotics


The world is experiencing a data revolution to discover knowledge in big data. Large scale neural networks are one of the mainstream tools of big data analytics. However, these methods causes much more energy for computation and memory than traditional computer vision algorithms. An energy efficient method to implement large-scale neural networks is highly demanded. RRAM (or memristor) and its crossbar structure provide a promising solution to perform the computation on memory and can significantly boost the energy/power efficiency of big data applications like neuromorphic computation and Deep Learning. The speaker will introduce energy efficient implementation of neural networks by taking advantage of the emerging RRAM technique. The main challenges and corresponding solutions of RRAM-based system design will be discussed in details. The speaker will present some recent results on kinds of energy efficient NNs based on RRAM, such as CNN, SNN, DNN and etc on a simulation platform. Some recent progress on chip design and planning to verify the above designs of RRAM-based neural networks will be introduced.

About this Lecture

Number of Slides:  100
Duration:  60 - 90 minutes
Languages Available:  English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.